Tool Calling
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
-0.8Delta Accuracy (ΔAcc)
7
May 12, 2026
-0.7Delta Accuracy
7
May 12, 2026
-0.3ΔAcc
7
May 12, 2026
70.4pass@1
7
Feb 26, 2026
51.96SoPR
7
Feb 26, 2026
57.7SoPR
7
Feb 26, 2026
20.7Average Score
6
Jun 19, 2026
80.9Average Score
6
Jun 19, 2026
53.9Average Score
6
Jun 19, 2026
92Accuracy
6
Feb 26, 2026
93.5Accuracy
6
Feb 26, 2026
18Base Accuracy
6
Jun 11, 2026
48.3Solvable Pass Rate
6
Feb 26, 2026
43.77TSR
4
Mar 18, 2026
61.31Exact Match (EM)
3
Apr 14, 2026
87.5Final Accuracy
3
Mar 18, 2026
91.33Avg Accuracy (3 patterns)
2
May 21, 2026
400P95 Latency (ms)
2
Apr 29, 2026
61.64Accuracy
2
Apr 14, 2026
55.43Simple Success Rate
2
Apr 10, 2026
96.5Success Rate (Python)
2
Mar 17, 2026
0.578Pass@1
2
Feb 26, 2026
61.8Pass@1
2
Feb 26, 2026
0.696Pass@1
2
Feb 26, 2026
73.6Pass@1
2
Feb 26, 2026